Knowledge Commons of Institute of Automation,CAS
Memory-Augmented Attention Model for Scene Text Recognition | |
Wang, Cong1,2; Yin, Fei1,2; Liu, Cheng-Lin1,2,3 | |
2018 | |
会议名称 | The 16th International Conference on Frontiers in Handwriting Recognition (ICFHR) |
会议日期 | August 5-8, 2018 |
会议地点 | Niagara Falls, USA |
摘要 | Natural scene text recognition is a very challenging task. Attention-based encoder-decoder framework has achieved the state-of-the-art performance. However, for some complex and/or low-quality images, the alignments estimated by the content-based attention network are not accurate enough, and so, the generated glimpse vector is also not powerful enough to represent the predicted character at current time step. To solve this problem, in the paper we propose a memory-augmented attention model for scene text recognition. The proposed memory-augmented attention network (MAAN) feeds the part of character sequence already generated and all attended alignment history to the attention model when predicting the character at current time step. The whole network can be trained end-to-end. Experimental results on several challenging benchmark datasets demonstrate that the proposed memory-augmented attention model for scene text recognition can achieve a comparable or better performance compared with state-of-the-art methods. |
关键词 | Scene Text Recognition Attention Network Memory Augmentation |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/38554 |
专题 | 多模态人工智能系统全国重点实验室_模式分析与学习 |
作者单位 | 1.中国科学院自动化研究所 2.中国科学院大学 3.中国科学院脑科学与智能技术卓越创新中心 |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Wang, Cong,Yin, Fei,Liu, Cheng-Lin. Memory-Augmented Attention Model for Scene Text Recognition[C],2018. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Memory-Augmented Att(1436KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论